Token pooling-aware training for multi-vector embedding models improves retrieval quality by teaching the encoder to preserve information when its vectors are merged, helping to retrieve better from the same storage budget. By applying a loss wrapper to a multi-vector retrieval loss, pooling-aware training can be used with existing models, resulting in a 97.8% retention of unpooled NanoBEIR nDCG@10 with a 4x reduction in document vectors. AI summary
Firehose
Filtered to Companies, tagged “token pooling” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives